rdkit

Core cheminformatics toolkit for SMILES/SDF/InChI parsing, descriptors (MW, LogP, TPSA), fingerprints, ECFP/Morgan fingerprints, substructure search, 2D/3D generation, similarity, reactions, and datamol-style molecule standardization when no separate wrapper skill is routed.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/rdkit/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with comprehensive executable examples, clear workflows, and well-organized progressive disclosure to real bundle files; the main weakness is repeated narrating prose that pads the token budget.

Suggestions

Trim or remove the one-line prose that restates what the following code block already shows (e.g. 'Convert molecules to text representations:', 'Read molecular structures from various formats:').

Move bulk enumerated API/SMARTS examples that overlap with the reference files out of SKILL.md, keeping only a representative example inline.

Add an explicit validate-fix-retry loop note for batch SDF/SMILES processing workflows to strengthen workflow validation.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with useful code blocks, but recurring narrating prose around each example (e.g. 'Convert molecules to text representations:', 'Read molecular structures from various formats:') and the overview restating what RDKit is add unnecessary explanation Claude already knows.	3 / 5
Actionability	The skill provides extensive copy-paste-ready, executable Python covering the common cases across I/O, descriptors, fingerprints, similarity, substructure search, reactions, conformers, and drawing.	5 / 5
Workflow Clarity	Multi-step workflows (drug-likeness, similarity screening, substructure filtering) are clearly sequenced with None-checks and error handling, though explicit validate-fix-retry feedback loops are limited rather than systematic.	4 / 5
Progressive Disclosure	Good structure with an overview plus capability sections, and clearly signaled one-level-deep references to three real reference files and three real scripts in the Resources section; a fair amount of API detail is still inlined that could live in the reference files.	4 / 5
	Total	16 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is highly specific with excellent trigger-term coverage and a clear, distinct niche, but it lacks an explicit 'Use when...' user-facing trigger clause, which limits its completeness score.

Suggestions

Add an explicit 'Use when...' clause with concrete user trigger phrases, e.g. 'Use when parsing or analyzing molecular structures, computing descriptors, or performing cheminformatics tasks like similarity search or substructure matching.'

Reframe the routing note as a separate boundary statement rather than relying on it to satisfy the 'when' requirement.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions including 'SMILES/SDF/InChI parsing', 'descriptors (MW, LogP, TPSA)', 'ECFP/Morgan fingerprints', 'substructure search', '2D/3D generation', 'similarity', 'reactions', and 'molecule standardization', giving comprehensive coverage of the toolkit's capabilities.	5 / 5
Completeness	It has a clear and detailed 'what', but no explicit 'Use when...' trigger clause; the only 'when' is the routing condition 'when no separate wrapper skill is routed', which addresses skill selection rather than user-facing triggers, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms ('ECFP/Morgan fingerprints') and file/format extensions ('SMILES/SDF/InChI') that a cheminformatics user would naturally say.	5 / 5
Distinctiveness Conflict Risk	The description carves out a clear RDKit cheminformatics niche and the 'when no separate wrapper skill is routed' clause reduces overlap risk with related wrapper skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (764 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/rdkit/SKILL.md
Commit: ddcaa2a

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.